←back to thread

A non-anthropomorphized view of LLMs

(addxorrol.blogspot.com)
475 points zdw | 2 comments | | HN request time: 0.414s | source
Show context
barrkel ◴[] No.44485012[source]
The problem with viewing LLMs as just sequence generators, and malbehaviour as bad sequences, is that it simplifies too much. LLMs have hidden state not necessarily directly reflected in the tokens being produced and it is possible for LLMs to output tokens in opposition to this hidden state to achieve longer term outcomes (or predictions, if you prefer).

Is it too anthropomorphic to say that this is a lie? To say that the hidden state and its long term predictions amount to a kind of goal? Maybe it is. But we then need a bunch of new words which have almost 1:1 correspondence to concepts from human agency and behavior to describe the processes that LLMs simulate to minimize prediction loss.

Reasoning by analogy is always shaky. It probably wouldn't be so bad to do so. But it would also amount to impenetrable jargon. It would be an uphill struggle to promulgate.

Instead, we use the anthropomorphic terminology, and then find ways to classify LLM behavior in human concept space. They are very defective humans, so it's still a bit misleading, but at least jargon is reduced.

replies(7): >>44485190 #>>44485198 #>>44485223 #>>44486284 #>>44487390 #>>44489939 #>>44490075 #
positron26 ◴[] No.44486284[source]
> Is it too anthropomorphic to say that this is a lie?

Yes. Current LLMs can only introspect from output tokens. You need hidden reasoning that is within the black box, self-knowing, intent, and motive to lie.

I rather think accusing an LLM of lying is like accusing a mousetrap of being a murderer.

When models have online learning, complex internal states, and reflection, I might consider one to have consciousness and to be capable of lying. It will need to manifest behaviors that can only emerge from the properties I listed.

I've seen similar arguments where people assert that LLMs cannot "grasp" what they are talking about. I strongly suspect a high degree of overlap between those willing to anthropomorphize error bars as lies while declining to award LLMs "grasping". Which is it? It can think or it cannot? (objectively, SoTA models today cannot yet.) The willingness to waffle and pivot around whichever perspective damns the machine completely belies the lack of honesty in such conversations.

replies(1): >>44486303 #
lostmsu ◴[] No.44486303[source]
> Current LLMs can only introspect from output tokens

The only interpretation of this statement I can come up with is plain wrong. There's no reason LLM shouldn't be able to introspect without any output tokens. As the GP correctly says, most of the processing in LLMs happens over hidden states. Output tokens are just an artefact for our convenience, which also happens to be the way the hidden state processing is trained.

replies(3): >>44486324 #>>44487399 #>>44487619 #
1. delusional ◴[] No.44487399[source]
> Output tokens are just an artefact for our convenience

That's nonsense. The hidden layers are specifically constructed to increase the probability that the model picks the right next word. Without the output/token generation stage the hidden layers are meaningless. Just empty noise.

It is fundamentally an algorithm for generating text. If you take the text away it's just a bunch of fmadds. A mute person can still think, an LLM without output tokens can do nothing.

replies(1): >>44503614 #
2. Tarq0n ◴[] No.44503614[source]
I think that's almost completely backwards. The input and output layers just convert between natural language and embeddings i.e. shift the format of the language. But operating on the embeddings is where meaning (locations in vector-space) are transformed.